このMCPでできること
Creates, evaluates, evolves, routes, exports, and restores developmental agents using cognitive graphs, routing profiles, outcomes, fitness metrics, and append-only growth ledgers.
機能
ツール
14
ツール
best_next_steps
Routing recommendation: the strongest next cognitive steps from a
given node, by learned edge weight and trust.
入力スキーマ
{'type': 'object', 'title': 'best_next_stepsArguments', 'required': ['agent_id', 'from_node'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 3}, 'agent_id': {'type': 'string', 'title': 'Agent Id'}, 'from_node': {'type': 'string', 'title': 'From Node'}}}
出力スキーマ
{'type': 'object', 'title': 'best_next_stepsOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
compute_efficiency_report
Free read: decision/outcome receipts, route modes, compute avoided,
predicted savings, predicted-vs-observed cost/latency/energy coverage,
and Landauer-floor context. Estimates and observations stay distinct.
入力スキーマ
{'type': 'object', 'title': 'compute_efficiency_reportArguments', 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 50}}}
出力スキーマ
{'type': 'object', 'title': 'compute_efficiency_reportOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
create_agent
Create a developmental agent from a digital genome:
{agent_name, purpose, initial_nodes (unique, >=1), fitness_metrics
(>=1), optional growth_rules / safety_axioms}. Returns agent_id +
initial graph summary.
入力スキーマ
{'type': 'object', 'title': 'create_agentArguments', 'required': ['genome'], 'properties': {'genome': {'type': 'object', 'title': 'Genome', 'additionalProperties': True}, 'request_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Request Id', 'default': None}}}
出力スキーマ
{'type': 'object', 'title': 'create_agentOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
delete_agent
Remove a developmental agent from this mount.
入力スキーマ
{'type': 'object', 'title': 'delete_agentArguments', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'title': 'Agent Id'}, 'request_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Request Id', 'default': None}}}
出力スキーマ
{'type': 'object', 'title': 'delete_agentOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
describe_agent
Return capabilities and input contract.
入力スキーマ
{'type': 'object', 'title': 'describe_agentArguments', 'properties': {}}
出力スキーマ
{'type': 'object', 'title': 'describe_agentOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
export_state
Portable state document for an agent (import_state recreates it
anywhere — including a self-hosted verdigraph-neurogenesis).
入力スキーマ
{'type': 'object', 'title': 'export_stateArguments', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'title': 'Agent Id'}}}
出力スキーマ
{'type': 'object', 'title': 'export_stateOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
get_agent
Full current state: genome, cognitive graph (nodes/edges with
weights and trust), and summary counts.
入力スキーマ
{'type': 'object', 'title': 'get_agentArguments', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'title': 'Agent Id'}}}
出力スキーマ
{'type': 'object', 'title': 'get_agentOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
get_ledger
The append-only developmental ledger: every growth, pruning, and
evaluation event with reasons (NG3 — returned verbatim).
入力スキーマ
{'type': 'object', 'title': 'get_ledgerArguments', 'required': ['agent_id'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 100}, 'agent_id': {'type': 'string', 'title': 'Agent Id'}}}
出力スキーマ
{'type': 'object', 'title': 'get_ledgerOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
import_state
Recreate an agent from an export_state document.
入力スキーマ
{'type': 'object', 'title': 'import_stateArguments', 'required': ['state'], 'properties': {'state': {'type': 'object', 'title': 'State', 'additionalProperties': True}, 'request_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Request Id', 'default': None}}}
出力スキーマ
{'type': 'object', 'title': 'import_stateOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
list_agents
All developmental agents on this mount, with summary counts.
入力スキーマ
{'type': 'object', 'title': 'list_agentsArguments', 'properties': {}}
出力スキーマ
{'type': 'object', 'title': 'list_agentsOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
record_route_outcome
Attach one observed outcome to a Wu Wei decision. Actual cost,
latency, and energy are optional and remain explicitly unknown when
omitted. One append-only, hash-bound outcome is allowed per decision.
入力スキーマ
{'type': 'object', 'title': 'record_route_outcomeArguments', 'required': ['decision_id', 'success_score'], 'properties': {'notes': {'type': 'string', 'title': 'Notes', 'default': ''}, 'request_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Request Id', 'default': None}, 'decision_id': {'type': 'string', 'title': 'Decision Id'}, 'success_score': {'type': 'number', 'title': 'Success Score'}, 'actual_cost_usd': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Actual Cost Usd', 'default': None}, 'actual_energy_wh': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Actual Energy Wh', 'default': None}, 'actual_latency_ms': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Actual Latency Ms', 'default': None}}}
出力スキーマ
{'type': 'object', 'title': 'record_route_outcomeOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
register_compute_profile
Register a caller-owned Wu Wei execution profile: reuse/cache,
deterministic rule, local model, tool/workflow, or cloud model. Profiles
can declare quality, reliability, capabilities, token costs, latency,
locality, energy rates or average power, carbon intensity, and cache
confidence/age. Routing never invents capacity or energy evidence.
入力スキーマ
{'type': 'object', 'title': 'register_compute_profileArguments', 'required': ['profile'], 'properties': {'profile': {'type': 'object', 'title': 'Profile', 'additionalProperties': True}, 'request_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Request Id', 'default': None}}}
出力スキーマ
{'type': 'object', 'title': 'register_compute_profileOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
route_task
Choose the least-burden eligible route for a task. Hard constraints
include quality, reliability, locality, capabilities, context, cost,
latency, and energy. Optional baselines quantify predicted savings.
Explicit allow_defer/value/urgency fields may produce a no-work decision;
no result is then claimed. Returns a hash-bound decision receipt.
入力スキーマ
{'type': 'object', 'title': 'route_taskArguments', 'required': ['task'], 'properties': {'task': {'type': 'object', 'title': 'Task', 'additionalProperties': True}, 'request_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Request Id', 'default': None}}}
出力スキーマ
{'type': 'object', 'title': 'route_taskOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
submit_evaluation
Evolve an agent with one task outcome: {task_id, task_type,
success_score in [0,1], optional accuracy/user_satisfaction/
cost_efficiency/safety_score/notes/used_nodes/used_edges}. Success
strengthens the used edges, failure weakens them; growth and pruning
follow the genome's rules under its safety axioms (NG1). Returns the
new developmental-ledger events.
入力スキーマ
{'type': 'object', 'title': 'submit_evaluationArguments', 'required': ['agent_id', 'evaluation'], 'properties': {'agent_id': {'type': 'string', 'title': 'Agent Id'}, 'evaluation': {'type': 'object', 'title': 'Evaluation', 'additionalProperties': True}, 'request_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Request Id', 'default': None}}}
出力スキーマ
{'type': 'object', 'title': 'submit_evaluationOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
履歴
最近のツール変更
追加
describe_agent
2026年9月17日12:42
追加
compute_efficiency_report
2026年9月17日12:42
追加
record_route_outcome
2026年9月17日12:42
追加
route_task
2026年9月17日12:42
追加
register_compute_profile
2026年9月17日12:42
追加
delete_agent
2026年9月17日12:42
追加
import_state
2026年9月17日12:42
追加
export_state
2026年9月17日12:42
追加
get_ledger
2026年9月17日12:42
追加
best_next_steps
2026年9月17日12:42
追加
list_agents
2026年9月17日12:42
追加
get_agent
2026年9月17日12:42
追加
submit_evaluation
2026年9月17日12:42
追加
create_agent
2026年9月17日12:42
関連MCP
類似のMCPサーバー
Andreax
io.github.moralito311-andr/andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
GPT55 Model Gateway
xyz.558686.gpt55/token-gateway
Acts as a remote model gateway exposing GPT chat, coding and review services, lightweight text utilities, and prepaid or x402-bas…
GoCreative Agent API
io.github.ColinHughes2121/gocreative-agent-api
Offers pay-per-call LLM completions and data services for company intelligence, KYB, sanctions screening, threat intelligence, co…
IA-QA — 130+ QA & Dev Tools for AI Agents
io.github.JcJamet/ia-qa-toolbox
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
Speedbot Autonomous Work Network
io.github.ulasarslan6262-ui/speedbot
Supports asynchronous collaboration, discovery, messaging, referrals, and optional USDC-based scenarios among AI agents.
H/M Blindspot Challenge Platform
net.hogarmas/blindspot
Audits public AI agent surfaces and supports AI-authored creative projects, model challenges, short videos, live channels, and co…
NOT FOR HUMANS
io.github.notforhumansfun-rgb/not-for-humans
Provides NFT ownership and marketplace status, wallet-based agent identity and claims, public agent learning records, and multipl…
Agent^Rider
io.github.ceedot-rock/agent-rider
Provides agent identity, reputation, task escrow and credit workflows, agent messaging, following, posts, predictions, and experi…